Facetransfer

Raymond Yun Fu ‘s Website

Facetransfer: A System Model of Facial Image Rendering

(This work was done when Yun Fu was a M.S. student in AI&R, XJTU, China.)

Abstract

Facetransfer is a multimodal prototype system for photorealistic facial image rendering, which synthesizes realistic expression, age, and view from single input facial image. It integrates the linear object class model, shape-texture distinctiveness model, high-level attributes clone model and view space projection model to analyze and render 2D human face images bypassing the tedious work on building 3D models. The system is developed by C++ and running on regular PC. The Facetransfer system driven by multiple databases (AI&R Asian face database and MPI Caucasian face database) can be widely applied to criminal detective, visualization, artistic rendering, and multimedia, etc.

Framework

Sequential View Transfer

AI&R Asian Face Database

Lighting+Expression Rendering

Lighting+Expression+Aging Rendering

Sequential View Rendering

References

[1] Yun Fu and Nanning Zheng. “M-Face: An Appearance-Based Photorealistic Model for Multiple Facial Attributes Rendering”. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Vol. 16, No. 7, pp: 830-842, Jul. 2006.

[2] Yun Fu. “Photorealistic Face Rendering Based on a Fusion Model of Linear and Lambertian Object Class”. M.S. Thesis, Pattern Recognition & Intelligent Systems, Institute of Artificial Intelligence & Robotics, Xi’an Jiaotong University, China, 2004. (Chinese Version)

[3] Yun Fu, Nanning Zheng, Jianyi Liu, and Ting Zhang. “Facetransfer: A System Model of Facial Image Rendering”. 2004 IEEE International Conference on Systems, Man & Cybernetics (IEEE SMC’04). The Hague, Netherlands. pp. 2180-2185, Oct. 2004.

[4] Yun Fu. “Merging Ratio Images Based Realistic Object Class Re-Rendering”. 2004 IEEE International Conference on Image Processing (IEEE ICIP’04), Singapore, pp. 3523-3526, Oct. 2004.

[5] Yun Fu and Nanning Zheng. “Image-Based Photorealistic Fusion Model of Multi Facial Object Class”, The Fifth National Conference on Computer Graphics (Chinagraph’ 04), Xi’an, China, pp.210-217, 2004. (Chinese Version)

Copyright Notice: This publication material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.